قسم الرياضيات و الإعلام الإلي

www.univ-soukahras.dz/ar/dept/mi

المقياس: Apprentissage automatique II

  1. معلومات
  2. الأسئلة
  3. التعليم عن بعد

Explain the term : Generalization in Machine Learning

0 votes

Explain the term : Generalization in Machine Learning mentioning the different aspects of generalization. Support your answer with examples.

نشر على 09:12, السبت 9 نوف 2019 By Imed BOUCHRIKA
In Apprentissage automatique II


أجوبة (5)




جواب (1)

0 votes

dans une botaniste, y a des arbre de la meme espece,, on va mesurer la hauteur et le tranc de chaque arbre, si on modelise les données trouvé on va deduire que la presentation est sous forme d'une droite, alors de la formule x=a*y+b ou a et b sont de constantes.

alors pour une nouvelle arable de la meme espece,  si on veut deduire sa hauteur, on se basant sur le tronc on peut calculer sa auteur selon la formule de la droite.

c'est la generalisation...? dsl pour la langue

نشر على 14:10, السبت 9 نوف 2019 by Ouahiba HANDEL
In Apprentissage automatique II



جواب (2)

0 votes

Generalization:

  • a fundamental element of learning.
  • The essential appearance of global learning for a situation on all sides.

the different aspects of generalization are:

  • size.
  • the environment.
  • equipment.

نشر على 19:05, السبت 9 نوف 2019 by Mouhamed Salah Ben khalfallah (14 points)
In Apprentissage automatique II



جواب (3)

0 votes

generalization: in a machine learning,the ability of an algorithme to be effective across a rang of inputs and applications.

aspects: 

size

environment

acquisition equipment

نشر على 15:34, الجمعة 15 نوف 2019 by belkis maarfia (25 points)
In Apprentissage automatique II



جواب (4)

0 votes

In machine learning, generalization usually refers to the ability of an algorithm to be effective across a range of inputs and applications.

As an example, say I were to show you an image of dog and ask you to “classify” that image for me; assuming you correctly identified it as a dog, would you still be able to identify it as a dog if I just moved the dog three pixels to the left? What about if I turned it upside? Would you still be able to identify the dog if I replaced it with a dog from a different breed? The answer to all of these questions is almost certainly because as humans, we generalize with incredible ease. On the other hand, machine learning very much struggles to do any of these things; it is only effective in classifying that one specific image.

نشر على 19:10, الخميس 12 ديس 2019 by noussaiba ledjemel (23 points)
In Apprentissage automatique II



جواب (5)

0 votes

generalisation is when the machine learning model does not encounter performance degradation  on the new input  from the same distribution of trained data , it all so refer the ability of an algorithem to be effective across a range of input and application(when we make an algorithm to a small database we can generalize this algorithm to other).

the aspect of generalasation are:

  • the environnemet
  • equipement
  • size

نشر على 21:42, الجمعة 3 ينا 2020 by sihem djélamda (9 points)
In Apprentissage automatique II



هل لديك جواب ?